arXiv Machine Learning August 27, 2026 By Haolan Guo, Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu

Sample Margin-Aware Recalibration of Temperature Scaling

Read the original on arXiv Machine Learning →

The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 10

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks

arXiv:2607. 07745v1 Announce Type: new Abstract: While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge.

By Arthur Chiron (IRIT, EPE UT), Franck Mamalet (IRIT, DTIPG - SNCF, UT3), Thomas Massena (IRIT, DTIPG - SNCF, UT3), Thomas Deltort (IRIT), Mathieu Serrurier (IRIT, UT2J)

benchmarks

arXiv Machine Learning

Aug 12

Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.

By Lening Zhao, Qipeng Zhan, Li Shen

computer-vision benchmarks

arXiv AI

Jun 2

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.

By Eug\`ene Berta, David Holzm\"uller, Francis Bach, Michael I. Jordan

computer-vision benchmarks

arXiv AI

Jun 30

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.

By Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge

benchmarks

arXiv Machine Learning

Jul 14

When does distribution shift break graph neural networks calibration?

arXiv:2607. 10804v1 Announce Type: new Abstract: Graph neural networks (GNNs) are increasingly deployed in real-world applications where distribution shift is un-avoidable.

By Abderaouf Bahi

benchmarks

arXiv AI

Sep 1

Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration

arXiv:2608.30230v1 Announce Type: new Abstract: Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sample via entropy minimization (EM) over multiple aug...

By Jungwon Choi, Hyeonseo Jang, Kibok Lee, Eunwoo Kim

benchmarks

One email a morning, machine-written

Related stories

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks

Invertible Logits Transformation for Accuracy-Preserving Post-Hoc Uncertainty Calibration

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

When does distribution shift break graph neural networks calibration?

Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration